The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Efficient handling of faults during operation is highly dependent on the interval (latency) from the time embedded instruments detect errors to the time when the fault manager localizes the errors. Detection and localization latencies are dependent on the network connecting fault-monitoring instruments to the fault manager. The network can be dedicated to fault-monitoring data, or used for functional...
Performance monitoring and fault detection systems are becoming more common in large photovoltaic (PV) plants as they can contribute to decreasing operation and maintenance costs, as well as for maximizing plant yield and lifetime. However, in case of residential and smaller commercial PV system applications the cost of the performance monitoring hardware and implementation is still high. Therefore,...
Fault detection and diagnosis methods have to deal with large variable data sets encountered in complex industrial systems. Solutions to this problem require multivariate statistics approaches often focused on the reduction of the space dimension. In this paper we propose a fault detection and estimation approach using Multivariate Kullback-Leibler Divergence (MKLD) to cope with the negative effects...
Dimension reduction is one of the important issues for soft sensor model construction based on data-driven method; especially for the high dimensional spectra data. To select effective input features with clear physical interpretation and simple model structure is very necessary. In this paper, a new feature selection method based on concurrent projection to latent structures (CPLS) algorithm is proposed...
Partial least squares (PLS) is a potential data-driven technique to deal with a huge number of measured variables and complex relationship. It could be used for process monitoring even for chemical processes that have nonlinear dynamic properties. In this paper PLS is applied to detect two fault types which occurred in real Acid Gas Removal Units (AGRU) of a gas separation process. The developed PLS-based...
An improved dynamic principal component analysis (DPCA) is presented which uses principal component related variable residual (PVR) statistic to replace Q statistic, applied to multivariate statistical process monitoring. The improved DPCA can avoid the conservation of Q statistical detection and provide more explicit process variable information about the principal component. Thus effectively identify...
This paper introduces a graph signal processing (GSP) framework for industrial process monitoring. Through a graph built to represent the variables of an industrial plant and their relationships, we show how to transform each sample vector observation using the graph Fourier transform (GFT) in order to infer the status of the plant. To validate the proposed method we compare it to the state of the...
In this paper a novel technique is proposed for online detection of timing interference in multicore architectures. The technique is aimed at mixed-criticality workloads. This paper describes a method to use hardware performance counters to detect such misbehaviors. Experimental data is gathered, showing the viability of this method. The method can be used as safety-net in several scheduling approaches.
This paper considers the problems of condition monitoring and fault detection in an existing solar photovoltaic (PV) plant in Australia. A PV prediction model is proposed to accurately model the PV plant output. This model is then used with three condition monitoring and fault detection methods. The considered methods involve comparison of measured and modeled voltage and current ratios with appropriate...
This paper presents a robust fault detection mechanism in EHV lines by using Wavelet transform and FFT analysis. db6 is chosen as mother wavelet since it is best one to analyze the transients during faults and load switching. The simulated results are validated with the experimental results. For fault detection 2nd harmonic spectral component and energy difference of the consecutive windows are used...
Fault detection is important for safe operation of various modern engineering systems. Partial least square (PLS) has been widely used in monitoring highly correlated process variables. Conventional PLS-based methods, nevertheless, often fail to detect incipient faults. In this paper, we develop new PLS-based monitoring chart, combining PLS with multivariate memory control chart, the multivariate...
For the multi-rate sampling systems with time series correlation data, a multi-rate fault detection algorithm based dynamic principal component analysis is proposed. The same sampling rate can be achieved in the algorithm by interpolation-filter-decimation, and then dynamic principal component analysis is implemented. The proposed method not only makes full use of the samples in a large number of...
Recently probabilistic principal component analysis (PPCA) has been used for process monitoring and fault diagnosis, which can model the process noise and can handle the problem of missing data in the probabilistic framework. Nevertheless, the missing data samples are treated as principal components in conventional PPCA method, which causes the estimation accuracy is largely influenced by data missing...
Reliability of a navigation system is one of greatimportance for navigation purposes. Therefore, anintegrity monitoring system is an inseparable part of aviation navigation system. Failures or faults due to malfunctions in the systems should be detected and repaired to keep the integrity of the system intact. In this paper, we present a method based on wavelet analysis for detecting failures. The...
Diabetes is a group of metabolic diseases which is harm to human health seriously. Continuous glucose monitoring (CGM) plays an important role in the treatment of diabetes. However, false information of glucose, caused by the faults of CGM, will reduce the treatment effect, and even lead diabetic patients to severe risks. So far, there are some notable attempts in the research of CGM fault detection...
Aiming at the multimode industrial process monitoring problem, this paper proposes a fault detection method based on local entropy principal component analysis (LEPCA) algorithm. Firstly, in order to deal with the multimode characteristic of operating data, k nearest neighbor Parzen window (kNN-Parzen) method is used to estimate each sample's local probability density. Then, a local relative density...
As PV systems gain popularity, more installers are in need of better, lighter and lower-cost measurement equipment that can be used to detect problems with PV modules and arrays both before and after installation. This paper describes the design and implementation of a portable I-V curve tracer based on MOSFETs, with the capability of measuring open-circuit voltages (Voc) up to 600 V, and short-circuit...
In order to produce the goods with high quality, the industrial system is becoming more complex than before. Meanwhile, the plant is suffering from high potential risks and the faults within it is difficult to be detected. Researchers have made efforts to diagnose the possible faults occurred in the system to further prevent the process from being broken down. Model-based method is proposed at the...
Recently, wireless sensor networks are being increasingly integrated with consumer electronic devices to deliver more intelligent services. Usually, the wireless sensor networks are expected to provide continuous, unattended service for months or even years. However, hardware reliability poses a major challenge to this expectation. To address this issue, this paper designs and implements a software-based...
The problem of mode monitoring in hybrid systems with application to fault detection problem solution is investigated. The hybrid systems under consideration consist of two parts characterized by discrete nondeterministic dynamics and nonlinear continuous dynamics. A given set of the faults is limited by possible wrong transitions from one mode to another. Solution of the mode monitoring problem is...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.